Check out the syllabus for all this information, including policies on academic honesty, accomodations, and late assignments.
- Meeting Times
-
Sondheim 206
Monday & Wednesday, 10:00 -- 11:15 AM
- Instructor
-
Frank Ferraro
ferraro [at] umbc [dot] edu
ITE 358
Monday 11:15 -- 12:00
by appointment
- TA
-
TBD
TBD [at] umbc [dot] edu
TBD
TBD
This course will cover state-of-the-art generative AI models, and methods for using them to "reason" about diverse problems of varying difficulty. The course will examine standard benchmark tasks across core machine learning, natural language processing and computer vision, along with new, domain-specific problems. Different prompting approaches, such as chain-of-thought and tree-of-thought, will be covered, as will different ways of incorporating feedback and training these models, through reinforcement learning from human feedback and preference optimization.
The following schedule is approximate, and subject to change. Slides, prior to the day of the class, may not be fully updated and also subject to change.